Downloads · 30 days
3.2K
100% of all-time downloads
ABot-Recon
acvlab/ABot-Recon
ABot-Recon is a image-to-3d model from acvlab. Use it for the image-to-3d task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
ABot-Recon is a streaming 3D reconstruction model that estimates camera motion and scene geometry online from extremely long videos using only a fixed local context of 12 frames. It predicts a point map in the current…
All-time downloads
3.2K
Public
Repo size
4 GB
Likes
22
Public
Repo makeup
Click a slice to open those files.
.safetensors4 GB · 100%
At a glance
- Task
- Image-to-3D
- License
- apache-2.0
- Model type
- abot_recon
- Access
- Public
- Created
- Aug 26, 2026
- Updated
- Sep 1, 2026
- SHA
- c69c26ca
Model card
From the Hugging Face model README
ABot-Recon
ABot-Recon is a streaming 3D reconstruction model that estimates camera motion and scene geometry online from extremely long videos using only a fixed local context of 12 frames. It predicts a point map in the current camera coordinate system and an adjacent-frame relative pose, then composes these local predictions into a global reconstruction through sequential composition.
Paper: Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction
Project page: ABot-Recon
Code: github.com/amap-cvlab/ABot-Recon
Quick Start
from pathlib import Path
from abot_recon import ABotRecon
images = sorted(Path("examples/images").glob("*.jpg"))
model = ABotRecon.from_pretrained(
"acvlab/ABot-Recon",
device="cuda",
attention_backend="auto",
loop_closure=False,
)
result = model.infer(images)
trajectory = result.camera_poses
relative_poses = result.relative_poses
local_points = result.local_points
confidence = result.confidence
For a full description of usage options, please refer to the GitHub README.
- Task
- Image-to-3D
- Type
- abot_recon
- License
- apache-2.0
- Created
- Aug 26, 2026
- Updated
- Sep 1, 2026